Anup Das
Anup Das
Assistant Professor, Drexel University


Compiler for Neuromorphic Computing


As learning models continue to scale aggressively, compiling a machine learning application to a non-volatile memory (NVM)-based neuromorphic hardware is becoming increasingly challenging. This talk will introduce nc2, a LLVM-based compiler for neuromorphic hardware designed with NVM synapses. Fundamental to this compiler is a novel unrolling technique, which decomposes a neuron function with large number of pre-synaptic connections into a sequence of homogeneous neural units, where each neural unit is a function computation node, accommodating up to two pre-synaptic connections. The unrolling technique ensures information integrity, resulting in no loss of model quality such as accuracy. Next, the unrolled machine learning model is partitioned into clusters, such that a cluster can fit onto a computation unit (e.g., crossbar) in the hardware, improving utilization of the crossbar's resources and reducing wasted energy. Finally, clusters are intelligently allocated to the hardware, reducing the performance bottleneck in time sharing the computation units.


Dr. Anup Das is an Assistant Professor at Drexel University. Between 2004 and 2011, he held positions in semiconductor industries like STMicrolelectronics and LSI Logic (now Broadcom), where he was involved in several stages of IC design: from RTL to GDS. He received a Ph.D. in Embedded Systems from National University of Singapore in 2014. Following his Ph.D., he was a post-doctoral fellow at the University of Southampton, UK and afterwards a researcher at IMEC, Netherlands, leading key projects related to neuromorphic computing. He received the NSF/DARPA real-time machine learning (RTML) award in 2019 for developing “operating systems” like framework for neuromorphic hardware. He is a recipient of the NSF CAREER award in 2020 to address the dependability aspect of neuromorphic computing both from software and hardware perspective. His other research interests include in- and near-memory computing with non-volatile memories. He is a senior member of the IEEE.